Optimization techniques to detect early ventilation extubation in intensive care units

The decision support models in intensive care units are developed to support medical staff in their decision making process. However, the optimization of these models is particularly difficult to apply due to dynamic, complex and multidisciplinary nature. Thus, there is a constant research and development of new algorithms capable of extracting knowledge from large volumes of data, in order to obtain better predictive results than the current algorithms. To test the optimization techniques a case study with real data provided by INTCare project was explored. This data is concerning to extubation cases. In this dataset, several models like Evolutionary Fuzzy Rule Learning, Lazy Learning, Decision Trees and many others were analysed in order to detect early extubation. The hydrids Decision Trees Genetic Algorithm, Supervised Classifier System and KNNAdaptive obtained the most accurate rate 93.2%, 93.1%, 92.97% respectively, thus showing their feasibility to work in a real environment.

IFN stimulated gene expression in the liver is a better predictor of treatment response in chronic hepatitis c than the IL28b (IFN lambda 3) genotype

Background: Therapy of chronic hepatitis C (CHC) with pegIFNa/ribavirin achieves sustained virologic response (SVR) in ~55%. Pre-activation of the endogenous interferon system in the liver is associated non-response (NR). Recently, genome-wide association studies described associations of allelic variants near the IL28B (IFNλ3) gene with treatment response and with spontaneous clearance of the virus. We investigated if the IL28B genotype determines the constitutive expression of IFN stimulated genes (ISGs) in the liver of patients with CHC. Methods: We genotyped 93 patients with CHC for 3 IL28B single nucleotide polymorphisms (SNPs, rs12979860, rs8099917, rs12980275), extracted RNA from their liver biopsies and quantified the expression of IL28B and of 8 previously identified classifier genes which discriminate between SVR and NR (IFI44L, RSAD2, ISG15, IFI22, LAMP3, OAS3, LGALS3BP and HTATIP2). Decision tree ensembles in the form of a random forest classifier were used to calculate the relative predictive power of these different variables in a multivariate analysis. Results: The minor IL28B allele (bad risk for treatment response) was significantly associated with increased expression of ISGs, and, unexpectedly, with decreased expression of IL28B. Stratification of the patients into SVR and NR revealed that ISG expression was conditionally independent from the IL28B genotype, i.e. there was an increased expression of ISGs in NR compared to SVR irrespective of the IL28B genotype. The random forest feature score (RFFS) identified IFI27 (RFFS = 2.93), RSAD2 (1.88) and HTATIP2 (1.50) expression and the HCV genotype (1.62) as the strongest predictors of treatment response. ROC curves of the IL28B SNPs showed an AUC of 0.66 with an error rate (ERR) of 0.38. A classifier with the 3 best classifying genes showed an excellent test performance with an AUC of 0.94 and ERR of 0.15. The addition of IL28B genotype information did not improve the predictive power of the 3-gene classifier. Conclusions: IL28B genotype and hepatic ISG expression are conditionally independent predictors of treatment response in CHC. There is no direct link between altered IFNλ3 expression and pre-activation of the endogenous system in the liver. Hepatic ISG expression is by far the better predictor for treatment response than IL28B genotype.

Intestinal content detection in capsule endoscopy using robust features

This work covers two aspects. First, it generally compares and summarizes the similarities and differences of state of the art feature detector and descriptor and second it presents a novel approach of detecting intestinal content (in particular bubbles) in capsule endoscopy images. Feature detectors and descriptors providing invariance to change of perspective, scale, signal-noise-ratio and lighting conditions are important and interesting topics in current research and the number of possible applications seems to be numberless. After analysing a selection of in the literature presented approaches, this work investigates in their suitability for applications information extraction in capsule endoscopy images. Eventually, a very good performing detector of intestinal content in capsule endoscopy images is presented. A accurate detection of intestinal content is crucial for all kinds of machine learning approaches and other analysis on capsule endoscopy studies because they occlude the field of view of the capsule camera and therefore those frames need to be excluded from analysis. As a so called “byproduct” of this investigation a graphical user interface supported Feature Analysis Tool is presented to execute and compare the discussed feature detectors and descriptor on arbitrary images, with configurable parameters and visualized their output. As well the presented bubble classifier is part of this tool and if a ground truth is available (or can also be generated using this tool) a detailed visualization of the validation result will be performed.

On the writer identification in old handwritten music scores

Report for the scientific sojourn at the University of Bern, Swiss, from Mars until June 2008. Writer identification consists in determining the writer of a piece of handwriting from a set of writers. Even though an important amount of compositions contains handwritten text in the music scores, the aim of the work is to use only music notation to determine the author. It’s been developed two approaches for writer identification in old handwritten music scores. The methods proposed extract features from every music line, and also features from a texture image of music symbols. First of all, the music sheet is first preprocessed for obtaining a binarized music score without the staff lines. The classification is performed using a k-NN classifier based on Euclidean distance. The proposed method has been tested on a database of old music scores from the 17th to 19th centuries, achieving encouraging identification rates.

Classification of human astrocytic gliomas on the basis of gene expression: a correlated group of genes with angiogenic activity emerges as a strong predictor of subtypes.

The development of targeted treatment strategies adapted to individual patients requires identification of the different tumor classes according to their biology and prognosis. We focus here on the molecular aspects underlying these differences, in terms of sets of genes that control pathogenesis of the different subtypes of astrocytic glioma. By performing cDNA-array analysis of 53 patient biopsies, comprising low-grade astrocytoma, secondary glioblastoma (respective recurrent high-grade tumors), and newly diagnosed primary glioblastoma, we demonstrate that human gliomas can be differentiated according to their gene expression. We found that low-grade astrocytoma have the most specific and similar expression profiles, whereas primary glioblastoma exhibit much larger variation between tumors. Secondary glioblastoma display features of both other groups. We identified several sets of genes with relatively highly correlated expression within groups that: (a). can be associated with specific biological functions; and (b). effectively differentiate tumor class. One prominent gene cluster discriminating primary versus nonprimary glioblastoma comprises mostly genes involved in angiogenesis, including VEGF fms-related tyrosine kinase 1 but also IGFBP2, that has not yet been directly linked to angiogenesis. In situ hybridization demonstrating coexpression of IGFBP2 and VEGF in pseudopalisading cells surrounding tumor necrosis provided further evidence for a possible involvement of IGFBP2 in angiogenesis. The separating groups of genes were found by the unsupervised coupled two-way clustering method, and their classification power was validated by a supervised construction of a nearly perfect glioma classifier.

Desenvolupament d'un memetracker - rastrejador de notícies

El projecte es centra en el desenvolupament d'un recol·lector de notícies publicades a una llarga llista de blocs ampliada contínuament pel desenvolupador i pels usuaris, afegint els seus blocs preferits. L'aplicació desenvolupada realitza una recol·lecció contínua de notícies consultant les possibles novetats que apareguin en cada un dels blocs inscrits a l'aplicació. Se'ls hi aplica un classificador per idioma i per temàtica i es relaciona amb les altres notícies existents si aquestes parlen sobre el mateix tema. En l'aplicació desenvolupada hi ha la possibilitat d'escollir entre les temàtiques ofertes i en l'idioma que ha estat publicada la notícia. Pel desenvolupament del projecte s'ha desitjat que la plataforma sigui el més compatible possible amb la tecnologia actual fent servir diversos llenguatges de programació que han permès desenvolupar cada un dels algorismes necessaris pel desenvolupament global de l'aplicació; en ordre d'ús he fet servir Php, Matlab, Html, MySql, CSS3, Javascript i XML. s'ha de destacar que el projecte aporta una comoditat per tots aquells lectors de blocs que es troben tantes vegades amb notícies ja llegides en els diferents blocs que consulten.

Cluster kernels for semisupervised classification of VHR urban images

In this paper, we present and apply a semisupervised support vector machine based on cluster kernels for the problem of very high resolution image classification. In the proposed setting, a base kernel working with labeled samples only is deformed by a likelihood kernel encoding similarities between unlabeled examples. The resulting kernel is used to train a standard support vector machine (SVM) classifier. Experiments carried out on very high resolution (VHR) multispectral and hyperspectral images using very few labeled examples show the relevancy of the method in the context of urban image classification. Its simplicity and the small number of parameters involved make it versatile and workable by unexperimented users.

Scene Classification Using a Hybrid Generative/Discriminative Approach

We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors' own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos

Effective diagnosis of Alzheimer's disease by means of large margin-based methodology.

BACKGROUND Functional brain images such as Single-Photon Emission Computed Tomography (SPECT) and Positron Emission Tomography (PET) have been widely used to guide the clinicians in the Alzheimer's Disease (AD) diagnosis. However, the subjectivity involved in their evaluation has favoured the development of Computer Aided Diagnosis (CAD) Systems. METHODS It is proposed a novel combination of feature extraction techniques to improve the diagnosis of AD. Firstly, Regions of Interest (ROIs) are selected by means of a t-test carried out on 3D Normalised Mean Square Error (NMSE) features restricted to be located within a predefined brain activation mask. In order to address the small sample-size problem, the dimension of the feature space was further reduced by: Large Margin Nearest Neighbours using a rectangular matrix (LMNN-RECT), Principal Component Analysis (PCA) or Partial Least Squares (PLS) (the two latter also analysed with a LMNN transformation). Regarding the classifiers, kernel Support Vector Machines (SVMs) and LMNN using Euclidean, Mahalanobis and Energy-based metrics were compared. RESULTS Several experiments were conducted in order to evaluate the proposed LMNN-based feature extraction algorithms and its benefits as: i) linear transformation of the PLS or PCA reduced data, ii) feature reduction technique, and iii) classifier (with Euclidean, Mahalanobis or Energy-based methodology). The system was evaluated by means of k-fold cross-validation yielding accuracy, sensitivity and specificity values of 92.78%, 91.07% and 95.12% (for SPECT) and 90.67%, 88% and 93.33% (for PET), respectively, when a NMSE-PLS-LMNN feature extraction method was used in combination with a SVM classifier, thus outperforming recently reported baseline methods. CONCLUSIONS All the proposed methods turned out to be a valid solution for the presented problem. One of the advances is the robustness of the LMNN algorithm that not only provides higher separation rate between the classes but it also makes (in combination with NMSE and PLS) this rate variation more stable. In addition, their generalization ability is another advance since several experiments were performed on two image modalities (SPECT and PET).

Technologies de procédé et de contrôle pour réduire la teneur en sel du jambon sec et des saucissons

Dans certains pays européens, les produits carnés élaborés peuvent représenter près de 20% de la consommation journalière de sodium. De ce fait, les industries de la viande tentent de réduire la teneur en sel dans les produits carnés pour répondre, d’une part aux attentes des consommateurs et d’autre part aux demandes des autorités sanitaires. Le système Quick‐Dry‐Slice process (QDS®), couplé avec l’utilisation de sels substituant le chlorure de sodium (NaCl), a permis de fabriquer, avec succès, des saucisses fermentées à basse teneur en sel en réduisant le cycle de fabrication et sans ajout de NaCl supplémentaire. Les technologies de mesure en ligne non destructives, comme les rayons X et l’induction électromagnétique, permettent de classifier les jambons frais suivant leur teneur en gras, un paramètre crucial pour adapter la durée de l’étape de salaison. La technologie des rayons X peut aussi être utilisée pour estimer la quantité de sel incorporée pendant la salaison. L’information relative aux teneurs en sel et en gras est importante pour optimiser le processus d’élaboration du jambon sec en réduisant la variabilité de la teneur en sel entre les lots et dans un même lot, mais aussi pour réduire la teneur en sel du produit final. D’autres technologies comme la spectroscopie en proche infrarouge (NIRS) ou spectroscopie microondes sont aussi utiles pour contrôler le processus d’élaboration et pour caractériser et classifier les produits carnés élaborés, selon leur teneur en sel. La plupart de ces technologies peuvent être facilement appliquées en ligne dans l’industrie afin de contrôler le processus de fabrication et d’obtenir ainsi des produits carnés présentant les caractéristiques recherchées.

Health effects of occupational exposure to traffic particles and noise

Exposure to fine particles and noise has been linked to cardiovascular diseases and elevated cardiovascular mortality affecting the worldwide population. Residence and/or work in proximity to emission sources as for example road traffic leads to an elevated exposure and a higher risk for adverse health effects. Highway maintenance workers spend most of their work time in traffic and are exposed regularly to particles and noise. The aims of this thesis were to provide a better understanding of the workers' mixed exposure to particles and noise and to assess cardiopulmonary short term health effects in relation to this exposure. Exposure and health data were collected in collaboration with 8 maintenance centers of the Swiss Road Maintenance Services located in the cantons Bern, Fribourg and Vaud in western Switzerland. Repeated measurements with 18 subjects were conducted during 50 non-consecutive work shifts between Mai 2010 and February 2012, equally distributed over all seasons. In the first part of this thesis we tested and validated measurements of ultrafine particles with a miniature diffusion size classifier (miniDiSC) - a novel particle counting device that was used for the exposure assessment during highway maintenance work. We found that particle numbers and average particle size measured by the miniDiSC were highly correlated with data from the P-TRAK, a condensation particle counter (CPC), as well as from a scanning mobility particle sizer (SMPS). However, the miniDiSC measured significantly more particles than the P-TRAK and significantly less than the SMPS in its full size range. Our data suggests that the instrument specific cutoffs were the main reason for the different particle counts. The first main objective of this thesis was to investigate the exposure of highway maintenance workers to air pollutants and noise, in relation to the different maintenance activities. We have seen that the workers are regularly exposed to high particle and noise levels. This was a consequence of close proximity to highway traffic and the use of motorized working equipment such as brush cutters, chain saws, generators and pneumatic hammers during which the highest exposure levels occurred. Although exposure to air pollutants were not critical if compared to occupational exposure limits, the elevated exposure to particles and noise may lead to a higher risk for cardiovascular diseases in this worker population. The second main objective was to investigate cardiopulmonary short-term health effects in relation to the particle and noise exposure during highway maintenance work. We observed a PM2.5 related increase of the acute-phase inflammation markers C-reactive protein and serum amyloid A and a decrease of TNFa. Heart rate variability increased as a consequence of particle as well as noise exposure. Increased high frequency power indicated a stronger parasympathetic influence on the heart. Elevated noise levels during recreational time, after work, were related to increased blood pressure. Our data confirmed that highway maintenance workers are exposed to elevated levels of particles and noise as compared to the average population. This exposure poses a cardiovascular health risk and it is therefore important to make efforts to better protect the workers health. The use of cleaner machines during maintenance work would be a major step to improve the workers' situation. Furthermore, regulatory policies with the aim of reducing combustion and non-combustion emissions from road traffic are important for the protection of workers in traffic environments and the entire population.

A genetic algorithm to ensemble feature selection

We are going to implement the "GA-SEFS" by Tsymbal and analyse experimentally its performance depending on the classifier algorithms used in the fitness function (NB, MNge, SMO). We are also going to study the effect of adding to the fitness function a measure to control complexity of the base classifiers.

Ambulatory monitoring of physical activities in patients with Parkinson's disease.

A new ambulatory method of monitoring physical activities in Parkinson's disease (PD) patients is proposed based on a portable data-logger with three body-fixed inertial sensors. A group of ten PD patients treated with subthalamic nucleus deep brain stimulation (STN-DBS) and ten normal control subjects followed a protocol of typical daily activities and the whole period of the measurement was recorded by video. Walking periods were recognized using two sensors on shanks and lying periods were detected using a sensor on trunk. By calculating kinematics features of the trunk movements during the transitions between sitting and standing postures and using a statistical classifier, sit-to-stand (SiSt) and stand-to-sit (StSi) transitions were detected and separated from other body movements. Finally, a fuzzy classifier used this information to detect periods of sitting and standing. The proposed method showed a high sensitivity and specificity for the detection of basic body postures allocations: sitting, standing, lying, and walking periods, both in PD patients and healthy subjects. We found significant differences in parameters related to SiSt and StSi transitions between PD patients and controls and also between PD patients with and without STN-DBS turned on. We concluded that our method provides a simple, accurate, and effective means to objectively quantify physical activities in both normal and PD patients and may prove useful to assess the level of motor functions in the latter.

Kernel-based methods for change detection in remote sensing images

Nowadays, the joint exploitation of images acquired daily by remote sensing instruments and of images available from archives allows a detailed monitoring of the transitions occurring at the surface of the Earth. These modifications of the land cover generate spectral discrepancies that can be detected via the analysis of remote sensing images. Independently from the origin of the images and of type of surface change, a correct processing of such data implies the adoption of flexible, robust and possibly nonlinear method, to correctly account for the complex statistical relationships characterizing the pixels of the images. This Thesis deals with the development and the application of advanced statistical methods for multi-temporal optical remote sensing image processing tasks. Three different families of machine learning models have been explored and fundamental solutions for change detection problems are provided. In the first part, change detection with user supervision has been considered. In a first application, a nonlinear classifier has been applied with the intent of precisely delineating flooded regions from a pair of images. In a second case study, the spatial context of each pixel has been injected into another nonlinear classifier to obtain a precise mapping of new urban structures. In both cases, the user provides the classifier with examples of what he believes has changed or not. In the second part, a completely automatic and unsupervised method for precise binary detection of changes has been proposed. The technique allows a very accurate mapping without any user intervention, resulting particularly useful when readiness and reaction times of the system are a crucial constraint. In the third, the problem of statistical distributions shifting between acquisitions is studied. Two approaches to transform the couple of bi-temporal images and reduce their differences unrelated to changes in land cover are studied. The methods align the distributions of the images, so that the pixel-wise comparison could be carried out with higher accuracy. Furthermore, the second method can deal with images from different sensors, no matter the dimensionality of the data nor the spectral information content. This opens the doors to possible solutions for a crucial problem in the field: detecting changes when the images have been acquired by two different sensors.

Interferon-Induced Gene Expression Is a Stronger Predictor of Treatment Response Than IL28B Genotype in Patients With Hepatitis C.

BACKGROUND & AIMS: The host immune response during the chronic phase of hepatitis C virus infection varies among individuals; some patients have a no interferon (IFN) response in the liver, whereas others have full activation IFN-stimulated genes (ISGs). Preactivation of this endogenous IFN system is associated with nonresponse to pegylated IFN-α (pegIFN-α) and ribavirin. Genome-wide association studies have associated allelic variants near the IL28B (IFNλ3) gene with treatment response. We investigated whether IL28B genotype determines the constitutive expression of ISGs in the liver and compared the abilities of ISG levels and IL28B genotype to predict treatment outcome. METHODS: We genotyped 109 patients with chronic hepatitis C for IL28B allelic variants and quantified the hepatic expression of ISGs and of IL28B. Decision tree ensembles, in the form of a random forest classifier, were used to calculate the relative predictive power of these different variables in a multivariate analysis. RESULTS: The minor IL28B allele was significantly associated with increased expression of ISG. However, stratification of the patients according to treatment response revealed increased ISG expression in nonresponders, irrespective of IL28B genotype. Multivariate analysis of ISG expression, IL28B genotype, and several other factors associated with response to therapy identified ISG expression as the best predictor of treatment response. CONCLUSIONS: IL28B genotype and hepatic expression of ISGs are independent predictors of response to treatment with pegIFN-α and ribavirin in patients with chronic hepatitis C. The most accurate prediction of response was obtained with a 4-gene classifier comprising IFI27, ISG15, RSAD2, and HTATIP2.